© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6890
    Prev
    Next
    INDEX
    Explanations

    information about violence statistics, such as gender-related violence and its prevalence in different types of relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1499
    +0.13
    0.4%
    468
    +0.12
    0.3%
    776
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.13
    0.07
    468
    +0.12
    0.05
    198
    +0.11
    0.06
    Negative Logits
     négociations
    -0.78
     nouveautés
    -0.70
     vœux
    -0.69
     ghz
    -0.67
     plais
    -0.64
     noël
    -0.63
     Româ
    -0.63
     téléchargement
    -0.62
     célé
    -0.60
     réunions
    -0.60
    POSITIVE LOGITS
     cases
    0.90
     incidents
    0.89
     instances
    0.86
     occurrences
    0.82
    cases
    0.74
     occurrence
    0.74
     occasions
    0.72
     encounters
    0.68
    instances
    0.67
     situations
    0.66
    Activations Density 0.642%

    No Known Activations