© 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. 489
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical-related terms or mentions of pharmacies

    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
    1865
    +0.09
    0.3%
    390
    +0.08
    0.3%
    1839
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1809
    +0.09
    0.02
    1210
    +0.08
    0.02
    1425
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.74
    +#+
    -0.57
     contend
    -0.56
    setClass
    -0.54
    </thead>
    -0.53
    skjaer
    -0.53
     Архивировано
    -0.53
    ็จ
    -0.53
     bring
    -0.53
    Liens
    -0.52
    POSITIVE LOGITS
     Pharma
    1.81
    Pharma
    1.67
     pharma
    1.64
     pharmacy
    1.56
     Pharmacy
    1.54
     Pharmaceutical
    1.53
     disagre
    1.53
     pharmaceutical
    1.50
     pharmacist
    1.49
     increa
    1.46
    Activations Density 0.148%

    No Known Activations