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

    Neuronpedia

    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. 6879
    Prev
    Next
    INDEX
    Explanations

    locations and events

    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
    1343
    +0.13
    0.4%
    906
    +0.12
    0.3%
    1741
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.13
    0.04
    371
    +0.12
    0.03
    1300
    +0.11
    0.02
    Negative Logits
     disreg
    -0.69
     purée
    -0.65
     subgoals
    -0.63
     vainly
    -0.61
     disambigu
    -0.60
     coarsely
    -0.59
     certitude
    -0.59
     anteriorly
    -0.59
     sclero
    -0.58
     blackish
    -0.58
    POSITIVE LOGITS
     Chapitre
    1.08
     Docteur
    1.02
     vété
    0.96
     Secrétaire
    0.95
     pixabay
    0.95
     élect
    0.89
     vôtre
    0.88
     Lég
    0.88
     vinyle
    0.86
     confé
    0.86
    Activations Density 0.078%

    No Known Activations