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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5048
    Prev
    Next
    INDEX
    Explanations

    information related to product prices and discounts

    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
    1871
    +0.26
    0.8%
    876
    +0.16
    0.5%
    678
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1871
    +0.26
    0.05
    678
    +0.16
    0.04
    876
    +0.14
    -0.00
    Negative Logits
     and
    -1.03
     in
    -1.01
    ,
    -1.01
     “
    -1.00
     for
    -0.99
     
    -0.99
     with
    -0.98
     but
    -0.98
     on
    -0.97
     by
    -0.96
    POSITIVE LOGITS
     !...
    2.92
     igno
    2.91
     dispen
    2.90
     dises
    2.90
     effe
    2.85
     embra
    2.81
     nutr
    2.81
     doman
    2.80
     ?...
    2.79
     erec
    2.78
    Activations Density 0.152%

    No Known Activations