© 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. 15192
    Prev
    Next
    INDEX
    Explanations

    technical terms related to geography, land surveys, mapping, development, and military equipment

    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
    512
    +0.08
    0.2%
    690
    +0.07
    0.2%
    1965
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    716
    +0.08
    0.02
    1207
    +0.07
    0.02
    911
    +0.07
    0.02
    Negative Logits
     emphat
    -1.28
     Mâ
    -1.20
     Juf
    -1.19
     Arro
    -1.16
     embra
    -1.14
     affor
    -1.14
     Sinal
    -1.12
     suspic
    -1.11
     inev
    -1.10
     Keny
    -1.10
    POSITIVE LOGITS
     higher
    0.85
     closer
    0.84
     longer
    0.78
    <bos>
    0.71
    更高
    0.69
    higher
    0.68
     more
    0.68
    もっと
    0.64
    delà
    0.63
     larger
    0.63
    Activations Density 0.343%

    No Known Activations