Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1168
    Prev
    Next
    INDEX
    Explanations

    concerns related to social issues and technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1043
    +0.11
    0.3%
    678
    +0.10
    0.3%
    438
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1043
    +0.11
    0.06
    678
    +0.10
    0.06
    1960
    +0.09
    0.03
    Negative Logits
     bunda
    -0.67
     ché
    -0.58
     vnd
    -0.57
     menta
    -0.57
     activer
    -0.57
     manda
    -0.56
     ria
    -0.56
     fent
    -0.55
     choi
    -0.55
     fei
    -0.54
    POSITIVE LOGITS
     pojaw
    0.77
     sentito
    0.74
     lasciato
    0.73
     regardant
    0.73
     sarili
    0.72
     tanong
    0.70
     ujedno
    0.67
     utaf
    0.66
     hjæl
    0.66
     papild
    0.64
    Activations Density 0.453%

    No Known Activations