© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4527
    Prev
    Next
    INDEX
    Explanations

    terms associated with creatures and their conditions or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1350
    +0.12
    0.4%
    678
    +0.11
    0.4%
    897
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1443
    +0.12
    0.05
    1350
    +0.11
    0.06
    1013
    +0.11
    0.09
    Negative Logits
    <bos>
    -2.02
    <eos>
    -0.77
    ↵↵
    -0.77
     U
    -0.74
     As
    -0.72
     So
    -0.72
     May
    -0.71
     including
    -0.71
     For
    -0.71
    .
    -0.70
    POSITIVE LOGITS
     tramont
    2.06
     haup
    1.94
     bandung
    1.94
     fluo
    1.90
     mef
    1.89
     napoli
    1.89
     frankfurt
    1.88
     soggior
    1.88
     sappi
    1.86
     wien
    1.84
    Activations Density 1.141%

    No Known Activations