© 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. 7502
    Prev
    Next
    INDEX
    Explanations

    pronouns and phrases related to personal preferences and individual choices

    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
    1978
    +0.14
    0.4%
    1919
    +0.10
    0.3%
    1990
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.14
    0.08
    1990
    +0.10
    0.05
    1415
    +0.08
    0.03
    Negative Logits
     الاطلاع
    -0.60
    Xar
    -0.58
    İstinadlar
    -0.56
    MessageOf
    -0.53
     Punj
    -0.49
     Jerez
    -0.49
     Rajah
    -0.48
    Togo
    -0.48
    providedIn
    -0.46
    Accès
    -0.46
    POSITIVE LOGITS
     pecuni
    0.66
     jugé
    0.63
     docteur
    0.61
     fiches
    0.61
     curé
    0.61
     juges
    0.59
     journées
    0.57
     photographe
    0.56
     configureStore
    0.56
     deems
    0.55
    Activations Density 0.260%

    No Known Activations