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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14470
    Prev
    Next
    INDEX
    Explanations

    verbs indicating past action

    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
    658
    +0.17
    0.5%
    478
    +0.17
    0.5%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.17
    0.13
    862
    +0.17
    0.06
    478
    +0.09
    0.07
    Negative Logits
     énon
    -0.63
     carrefour
    -0.63
     démoc
    -0.61
     pleins
    -0.58
     écout
    -0.58
     Fixation
    -0.56
     Inscription
    -0.54
    stasia
    -0.54
     hcm
    -0.54
    umum
    -0.53
    POSITIVE LOGITS
     able
    1.04
     unable
    0.78
    unable
    0.73
     willing
    0.72
     aware
    0.68
    Able
    0.65
     كومونز
    0.64
     ghz
    0.63
     tasked
    0.61
     glad
    0.61
    Activations Density 0.488%

    No Known Activations