© 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. 7734
    Prev
    Next
    INDEX
    Explanations

    information related to sleep tracking devices or systems

    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
    1385
    +0.16
    0.5%
    876
    +0.14
    0.4%
    1842
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.16
    0.04
    394
    +0.14
    0.04
    1385
    +0.12
    0.04
    Negative Logits
     pamph
    -1.29
     Juf
    -1.17
     poichè
    -1.13
     accla
    -1.11
     reluct
    -1.07
     gaily
    -1.07
     Souha
    -1.04
     Shakspeare
    -1.04
     Mahomet
    -1.04
     Abbé
    -1.03
    POSITIVE LOGITS
     detected
    0.75
     detect
    0.73
     detection
    0.67
     sensors
    0.67
     sensor
    0.64
     detecting
    0.63
     detects
    0.58
     signals
    0.57
     sensing
    0.56
     measurements
    0.55
    Activations Density 0.355%

    No Known Activations