© 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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14128
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical violence and crime

    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
    1334
    +0.13
    0.4%
    1896
    +0.13
    0.4%
    161
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.13
    0.08
    161
    +0.13
    0.05
    395
    +0.12
    0.06
    Negative Logits
    หน้านี้
    -0.49
     IOError
    -0.49
    DisplayMetrics
    -0.48
     Routed
    -0.48
     względu
    -0.45
    ThroughAttribute
    -0.45
    Asimismo
    -0.45
    amzn
    -0.44
     كومونز
    -0.43
     Cæsar
    -0.43
    POSITIVE LOGITS
     giapp
    0.68
     scrat
    0.67
     naer
    0.67
     nemici
    0.66
     bonté
    0.62
     anse
    0.61
    reador
    0.61
     popoli
    0.61
     sentimenti
    0.60
     disreg
    0.60
    Activations Density 0.311%

    No Known Activations