© 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. 13770
    Prev
    Next
    INDEX
    Explanations

    comparisons between natural and chemical substances, as well as mentions of age groups and specific gender identities

    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
    1343
    +0.11
    0.3%
    198
    +0.10
    0.3%
    1967
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.11
    0.04
    1473
    +0.10
    0.02
    1806
    +0.08
    0.03
    Negative Logits
     fuf
    -1.67
     reluct
    -1.65
     Intere
    -1.61
     disagre
    -1.60
     depic
    -1.59
     desir
    -1.56
     increa
    -1.55
     inev
    -1.53
     emphat
    -1.53
     ?...
    -1.52
    POSITIVE LOGITS
     otherwise
    0.65
    setOpaque
    0.62
    ഉ
    0.61
     alike
    0.61
    بالإنجليزية
    0.60
    بالإ
    0.60
     ones
    0.60
    película
    0.59
     viewWillAppear
    0.59
     beyond
    0.59
    Activations Density 0.140%

    No Known Activations