© 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. 13776
    Prev
    Next
    INDEX
    Explanations

    phrases related to political issues or conflicts

    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
    674
    +0.14
    0.4%
    856
    +0.11
    0.3%
    228
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1045
    +0.14
    0.03
    924
    +0.11
    0.04
    1323
    +0.10
    0.03
    Negative Logits
     maneu
    -1.37
     depic
    -1.36
     alre
    -1.34
     fte
    -1.33
     increa
    -1.31
     fto
    -1.29
     secon
    -1.27
     deleter
    -1.27
     volunte
    -1.27
     shenan
    -1.26
    POSITIVE LOGITS
    <bos>
    1.12
    PerformLayout
    1.05
     <>",
    0.78
    }}$\\
    0.71
    !="")
    0.71
    GraphicsUnit
    0.70
    /}.
    0.70
    MarshalTo
    0.67
    IContainer
    0.67
     panahon
    0.67
    Activations Density 0.284%

    No Known Activations