© 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. 3317
    Prev
    Next
    INDEX
    Explanations

    words related to the seasons, particularly focusing on the transition from summer to winter

    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
    227
    +0.11
    0.3%
    1177
    +0.11
    0.3%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1662
    +0.11
    0.06
    1885
    +0.11
    0.04
    1499
    +0.10
    0.05
    Negative Logits
     estekak
    -0.59
     >=",
    -0.56
     solidar
    -0.55
     diverti
    -0.55
     ortop
    -0.55
     utop
    -0.55
     pittores
    -0.54
     incess
    -0.54
     fatica
    -0.53
     respekt
    -0.53
    POSITIVE LOGITS
     elsewhere
    0.98
     shewn
    0.72
     Shakspeare
    0.70
     Elsewhere
    0.68
     sovere
    0.68
     unwarran
    0.66
     effectually
    0.63
     quitted
    0.61
     aught
    0.60
     ở
    0.60
    Activations Density 0.578%

    No Known Activations