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. 13188
    Prev
    Next
    INDEX
    Explanations

    instances where violent acts are described

    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
    1177
    +0.14
    0.4%
    964
    +0.13
    0.4%
    946
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.14
    0.10
    415
    +0.13
    0.06
    1487
    +0.13
    0.08
    Negative Logits
    IsContent
    -0.64
    hability
    -0.59
     ModelExpression
    -0.57
    ‌.
    -0.56
    InputTagHelper
    -0.56
     tamaños
    -0.55
    ipedi
    -0.55
     áng
    -0.54
     (?,
    -0.54
    rativa
    -0.53
    POSITIVE LOGITS
     Juf
    1.36
     apprehen
    1.23
     McLaugh
    1.23
     encomp
    1.21
     Bartholo
    1.20
     Gorb
    1.20
     reluct
    1.19
     Daven
    1.16
     disagre
    1.14
     depic
    1.13
    Activations Density 1.007%

    No Known Activations