© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1060
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or decisions to be made

    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
    1309
    +0.08
    0.2%
    1989
    +0.08
    0.2%
    599
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.08
    0.05
    1989
    +0.08
    0.03
    932
    +0.07
    0.03
    Negative Logits
     increa
    -2.09
     guarante
    -2.05
     reluct
    -2.02
     affor
    -1.98
     hairc
    -1.96
     disagre
    -1.91
     unlaw
    -1.90
     unden
    -1.89
     swarovski
    -1.89
     ecru
    -1.88
    POSITIVE LOGITS
    XMLSchema
    0.75
     whether
    0.75
     CreateTagHelper
    0.74
    PYX
    0.72
    principalColumn
    0.71
     evaluate
    0.69
     архивлан
    0.69
    Diweddarwch
    0.68
     decide
    0.68
    IsContent
    0.68
    Activations Density 0.283%

    No Known Activations