© 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. 7432
    Prev
    Next
    INDEX
    Explanations

    text related to technical instructions or information

    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
    382
    +0.09
    0.3%
    674
    +0.09
    0.3%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.09
    0.05
    897
    +0.09
    0.04
    1336
    +0.09
    0.04
    Negative Logits
     ideolog
    -0.93
     uhr
    -0.83
     sensibili
    -0.82
     pecuni
    -0.80
     republi
    -0.80
     solidar
    -0.79
     vapore
    -0.79
     circon
    -0.78
    cedures
    -0.78
     BIBSYS
    -0.78
    POSITIVE LOGITS
     of
    0.90
     McLaugh
    0.66
     ofthe
    0.63
     của
    0.62
    OfThe
    0.60
     McInt
    0.58
     thereof
    0.57
    ofthe
    0.57
     mossy
    0.56
    cutie
    0.56
    Activations Density 0.172%

    No Known Activations