© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 602
    Prev
    Next
    INDEX
    Explanations

    words related to entertainment or events that could provoke strong emotional reactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    667
    +0.08
    0.2%
    1721
    +0.08
    0.2%
    15
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.03
    1363
    +0.08
    0.05
    1343
    +0.07
    0.06
    Negative Logits
    RTSC
    -0.89
     Obrador
    -0.87
    awtextra
    -0.81
    WebControls
    -0.81
    twimg
    -0.78
     jScrollPane
    -0.78
    rrggbb
    -0.76
    EndContext
    -0.75
    ItemLayout
    -0.74
    adaptiveStyles
    -0.72
    POSITIVE LOGITS
     shenan
    2.82
     impra
    2.64
     hairc
    2.64
     reluct
    2.57
     snoopy
    2.57
     milf
    2.51
     affor
    2.46
     maneu
    2.46
     increa
    2.46
     disagre
    2.43
    Activations Density 0.396%

    No Known Activations