© 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 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. 14869
    Prev
    Next
    INDEX
    Explanations

    architectural or construction-related terms and descriptions

    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
    906
    +0.13
    0.4%
    1385
    +0.10
    0.3%
    1539
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.13
    0.05
    2044
    +0.10
    0.06
    736
    +0.08
    0.05
    Negative Logits
     vogli
    -0.87
     proprement
    -0.86
     doman
    -0.86
     saar
    -0.85
     allarg
    -0.85
     parteci
    -0.84
     succede
    -0.84
     endom
    -0.83
     uhr
    -0.82
     embra
    -0.82
    POSITIVE LOGITS
     position
    0.80
     positioned
    0.77
    position
    0.76
     near
    0.76
     closer
    0.67
     close
    0.66
    位置
    0.65
     within
    0.64
     placed
    0.63
     위치
    0.63
    Activations Density 0.420%

    No Known Activations