© 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. 14395
    Prev
    Next
    INDEX
    Explanations

    sentences discussing changes or reforms in structures or systems

    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
    599
    +0.17
    0.6%
    1978
    +0.14
    0.5%
    845
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.17
    0.06
    1129
    +0.14
    0.05
    845
    +0.11
    0.03
    Negative Logits
     impra
    -1.18
     stockholm
    -1.17
     |]
    -1.16
     Juf
    -1.15
     erad
    -1.14
     tsl
    -1.13
     casio
    -1.12
     strick
    -1.11
     bangkok
    -1.11
     suscep
    -1.10
    POSITIVE LOGITS
     [
    0.73
    ,"
    0.72
    ,”
    0.72
     really
    0.69
    </em>
    0.64
     everybody
    0.59
     ['
    0.59
    [
    0.58
    </i>
    0.58
     somebody
    0.58
    Activations Density 0.279%

    No Known Activations