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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13723
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, events, and groups

    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
    1150
    +0.12
    0.4%
    227
    +0.12
    0.3%
    764
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.07
    648
    +0.12
    0.04
    113
    +0.09
    0.04
    Negative Logits
    middels
    -0.81
     écout
    -0.78
     télécharge
    -0.74
     évit
    -0.73
     considér
    -0.72
     regardant
    -0.71
     décid
    -0.70
    Mittwoch
    -0.67
     appréci
    -0.67
    Donnerstag
    -0.65
    POSITIVE LOGITS
     Interpreting
    0.51
     errone
    0.51
     Evaluations
    0.49
     Causal
    0.47
     Occurrence
    0.46
     sophistic
    0.46
     Ltd
    0.46
     evoc
    0.45
     depic
    0.45
     Impaired
    0.45
    Activations Density 0.256%

    No Known Activations