© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 835
    Prev
    Next
    INDEX
    Explanations

    mentions of scary or frightening topics and scenarios

    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
    50
    +0.11
    0.5%
    381
    +0.07
    0.3%
    1343
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.08
    736
    +0.07
    0.07
    678
    +0.06
    0.06
    Negative Logits
    <bos>
    -1.30
     fået
    -0.91
     brengt
    -0.84
    },{
    -0.84
     sagde
    -0.83
     fortæller
    -0.80
     vertelt
    -0.79
    }],
    -0.78
     gik
    -0.77
     levert
    -0.77
    POSITIVE LOGITS
     habile
    1.43
     maneu
    1.40
     impra
    1.35
     affor
    1.35
     disreg
    1.32
     resear
    1.32
     OGS
    1.28
     accla
    1.25
     emphat
    1.25
     philanth
    1.23
    Activations Density 0.342%

    No Known Activations