© 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. 3755
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or making decisions

    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
    1577
    +0.16
    0.5%
    1978
    +0.14
    0.4%
    1314
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.16
    0.02
    505
    +0.14
    0.01
    155
    +0.14
    0.04
    Negative Logits
    Fonto
    -0.57
    HasAnnotation
    -0.57
    SharedDtor
    -0.56
    Ikus
    -0.56
    }],
    -0.56
    WithIOException
    -0.55
    TemporalType
    -0.54
    Gén
    -0.54
    Acab
    -0.53
    Morfo
    -0.53
    POSITIVE LOGITS
     thut
    1.53
     fta
    1.43
     fto
    1.41
     fuf
    1.41
     swarovski
    1.40
     disagre
    1.39
     increa
    1.39
     effe
    1.38
     greate
    1.38
     inev
    1.37
    Activations Density 0.537%

    No Known Activations