© 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. 962
    Prev
    Next
    INDEX
    Explanations

    participles ending in '-ed' referring to actions or descriptions

    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
    1166
    +0.09
    0.3%
    1392
    +0.08
    0.3%
    667
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1142
    +0.09
    0.04
    1512
    +0.08
    0.05
    1271
    +0.08
    0.06
    Negative Logits
     BoxFit
    -0.73
    setVerticalGroup
    -0.73
    DatabaseError
    -0.67
    zzar
    -0.63
    IsContent
    -0.62
    Autoritní
    -0.61
    PyExc
    -0.60
    decer
    -0.59
    testify
    -0.59
    RUnlock
    -0.58
    POSITIVE LOGITS
     maneu
    2.17
     shenan
    2.16
     intersper
    2.07
     encomp
    2.07
     reluct
    1.99
     depic
    1.96
     increa
    1.96
     apprehen
    1.93
     snoopy
    1.92
     milf
    1.91
    Activations Density 0.731%

    No Known Activations