© 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. 13778
    Prev
    Next
    INDEX
    Explanations

    phrases related to putting something into action or emphasizing a significant impact

    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
    1950
    +0.11
    0.3%
    562
    +0.09
    0.3%
    421
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.11
    0.04
    562
    +0.09
    0.03
    1950
    +0.08
    0.04
    Negative Logits
     Châ
    -0.56
     catég
    -0.55
     Mémoires
    -0.54
     Vaux
    -0.54
    '';
    -0.52
     akti
    -0.52
     Bré
    -0.51
     %\
    -0.51
     elek
    -0.51
     Autre
    -0.51
    POSITIVE LOGITS
     put
    0.84
     puts
    0.79
     PUT
    0.76
     putting
    0.76
    putting
    0.73
    Putting
    0.72
    put
    0.71
    PUT
    0.71
     Put
    0.69
    Put
    0.68
    Activations Density 0.145%

    No Known Activations