© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 615
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and cultural terms related to religious contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    966
    +0.13
    0.5%
    50
    +0.13
    0.5%
    896
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.06
    1343
    +0.13
    0.06
    1731
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.61
     krishna
    -1.15
     kumar
    -0.96
    ahalli
    -0.96
     singh
    -0.88
     Punj
    -0.85
    krish
    -0.83
     bhai
    -0.79
     mumbai
    -0.76
     SINGH
    -0.73
    POSITIVE LOGITS
     Bartholo
    1.42
     pamph
    1.42
     Şi
    1.40
     fep
    1.39
     inconce
    1.38
     Abbé
    1.38
     Daven
    1.37
     affor
    1.37
     Shakspeare
    1.36
     Sinal
    1.36
    Activations Density 0.252%

    No Known Activations