© 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. 14387
    Prev
    Next
    INDEX
    Explanations

    information related to horticulture and regional locations

    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
    764
    +0.39
    1.4%
    599
    +0.28
    1.1%
    227
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.39
    0.07
    599
    +0.28
    0.04
    227
    +0.15
    0.04
    Negative Logits
     ErrIntOverflow
    -0.58
     Walkover
    -0.57
    parsedMessage
    -0.57
    Искәрмәләр
    -0.56
     שוליים
    -0.56
     jsPsych
    -0.55
    aarrggbb
    -0.52
    LookAnd
    -0.51
     Савезне
    -0.51
    Erreferentziak
    -0.50
    POSITIVE LOGITS
     yoda
    0.70
     swee
    0.68
     imgur
    0.66
     ftw
    0.65
     ferrari
    0.65
     erad
    0.65
     getty
    0.64
     vhs
    0.64
     Moderately
    0.64
     coq
    0.63
    Activations Density 0.217%

    No Known Activations