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. 3291
    Prev
    Next
    INDEX
    Explanations

    policy-related terms and discussions

    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
    604
    +0.20
    0.6%
    939
    +0.11
    0.3%
    1984
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1424
    +0.20
    0.06
    939
    +0.11
    0.07
    934
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.19
     !...
    -1.08
     ?...
    -1.05
     congr
    -1.04
     vhs
    -1.02
     desir
    -0.98
     emphat
    -0.97
     casio
    -0.93
     paff
    -0.93
     ftw
    -0.92
    POSITIVE LOGITS
     threat
    0.61
     escalation
    0.60
     threats
    0.59
     retaliation
    0.56
     escalate
    0.55
     nuclear
    0.54
     retali
    0.54
    bollah
    0.50
    Galería
    0.50
     threatened
    0.50
    Activations Density 0.622%

    No Known Activations