© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 494
    Prev
    Next
    INDEX
    Explanations

    statements of intention or announcements about future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.32
    1.2%
    1177
    +0.21
    0.8%
    453
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.32
    0.06
    781
    +0.21
    0.05
    1177
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.70
    ⓧ
    -0.83
    /**
    -0.83
     !...
    -0.70
    <?
    -0.65
     overcrow
    -0.62
     devin
    -0.60
     balle
    -0.59
     devine
    -0.58
     fap
    -0.57
    POSITIVE LOGITS
     Jambi
    1.00
     Lampung
    1.00
     Palembang
    0.98
     Minang
    0.96
     Banjar
    0.93
     Muhamma
    0.93
     Karang
    0.92
     Pekan
    0.92
     Riau
    0.88
     Tangerang
    0.88
    Activations Density 0.507%

    No Known Activations