© 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. 904
    Prev
    Next
    INDEX
    Explanations

    descriptions of places with historical, natural, or cultural significance

    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
    478
    +0.22
    0.7%
    2019
    +0.12
    0.4%
    690
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.22
    0.08
    658
    +0.12
    0.06
    1937
    +0.09
    0.05
    Negative Logits
     viendra
    -1.14
     territo
    -1.07
     maksi
    -1.07
     exé
    -1.03
     pleins
    -1.03
     préc
    -1.00
     Intere
    -0.97
     prendra
    -0.97
     éto
    -0.96
     hcm
    -0.95
    POSITIVE LOGITS
     nonetheless
    0.74
     nevertheless
    0.69
     undoubtedly
    0.61
     able
    0.60
     welcomed
    0.59
     poised
    0.59
     useCallback
    0.57
     seen
    0.56
     unlikely
    0.56
     destined
    0.56
    Activations Density 0.499%

    No Known Activations