© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3485
    Prev
    Next
    INDEX
    Explanations

    medical conditions, health-related terms, and impactful events

    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
    1919
    +0.10
    0.3%
    1499
    +0.10
    0.3%
    297
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.10
    0.07
    1919
    +0.10
    0.06
    862
    +0.08
    0.03
    Negative Logits
     utop
    -0.90
     meras
    -0.85
     prostitu
    -0.83
     hunde
    -0.82
     asim
    -0.82
     rimb
    -0.81
     solidar
    -0.80
     persil
    -0.79
     alkoh
    -0.79
     tenda
    -0.78
    POSITIVE LOGITS
     was
    0.81
     became
    0.80
     were
    0.79
     remained
    0.78
     becomes
    0.76
     underwent
    0.74
     will
    0.71
     could
    0.71
     undergoes
    0.71
     zostać
    0.70
    Activations Density 0.496%

    No Known Activations