© 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. 569
    Prev
    Next
    INDEX
    Explanations

    references to specific biblical figures and texts

    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
    1350
    +0.09
    0.3%
    172
    +0.09
    0.3%
    1616
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.09
    0.02
    1120
    +0.09
    0.02
    1056
    +0.08
    0.02
    Negative Logits
     fix
    -0.82
     encourage
    -0.80
     led
    -0.78
    .
    -0.77
     find
    -0.77
     expand
    -0.76
     manage
    -0.75
     get
    -0.75
    ,
    -0.74
     add
    -0.74
    POSITIVE LOGITS
     wien
    1.86
     mef
    1.83
     „,
    1.83
     fluo
    1.83
     bourgeo
    1.82
     viciss
    1.81
     eiffel
    1.80
     Intere
    1.78
     FFFF
    1.78
     dises
    1.78
    Activations Density 0.152%

    No Known Activations