© 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. 6810
    Prev
    Next
    INDEX
    Explanations

    technical details and discussions

    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
    674
    +0.13
    0.4%
    1328
    +0.13
    0.4%
    1127
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1127
    +0.13
    0.05
    1865
    +0.13
    0.05
    1472
    +0.13
    0.04
    Negative Logits
     peculi
    -1.12
     priva
    -1.11
     meis
    -1.08
     alkoh
    -1.08
     fere
    -1.04
     ivi
    -1.04
     Violon
    -1.02
     meras
    -1.02
     parati
    -1.01
     bont
    -1.01
    POSITIVE LOGITS
     Or
    0.93
    Or
    0.82
    or
    0.79
     OR
    0.78
     or
    0.75
    <bos>
    0.70
     alternatively
    0.69
     maybe
    0.67
     else
    0.64
     perhaps
    0.64
    Activations Density 0.144%

    No Known Activations