© 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. 15173
    Prev
    Next
    INDEX
    Explanations

    comparisons or confrontations between entities

    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
    507
    +0.11
    0.3%
    1441
    +0.09
    0.3%
    1314
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1441
    +0.11
    0.05
    507
    +0.09
    0.04
    1409
    +0.09
    0.02
    Negative Logits
     nece
    -0.65
     dichi
    -0.65
     apparti
    -0.60
     parteci
    -0.58
     unwarran
    -0.56
     adh
    -0.56
     sopr
    -0.55
     dovr
    -0.55
     aen
    -0.55
     aspetta
    -0.54
    POSITIVE LOGITS
     rivalry
    0.90
     vying
    0.86
     competing
    0.80
     competition
    0.79
     rival
    0.78
     rivals
    0.76
     showdown
    0.75
     battle
    0.74
     duel
    0.74
     competitors
    0.71
    Activations Density 0.653%

    No Known Activations