© 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. 1045
    Prev
    Next
    INDEX
    Explanations

    speech patterns and quotes involving casual conversation and information sharing

    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
    814
    +0.10
    0.3%
    1637
    +0.10
    0.3%
    381
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.10
    0.02
    814
    +0.10
    0.01
    493
    +0.09
    0.02
    Negative Logits
     hina
    -1.23
     kani
    -1.21
     effe
    -1.19
     illi
    -1.17
     daf
    -1.15
     mef
    -1.15
     huma
    -1.13
     bett
    -1.13
     alre
    -1.12
     dises
    -1.12
    POSITIVE LOGITS
    <bos>
    0.69
     maybe
    0.66
     like
    0.59
     stuff
    0.59
     tudom
    0.55
     knowing
    0.55
     kinda
    0.54
     yeah
    0.53
    maybe
    0.52
     just
    0.52
    Activations Density 0.067%

    No Known Activations