© 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. 873
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement, specifically rolling, and the direction of that movement

    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
    481
    +0.14
    0.6%
    68
    +0.12
    0.5%
    869
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.14
    0.04
    703
    +0.12
    0.03
    1618
    +0.12
    0.02
    Negative Logits
     Justus
    -0.46
     Zuh
    -0.43
     Petra
    -0.42
     Basili
    -0.42
    asyarakat
    -0.41
     Hauts
    -0.41
     XXVI
    -0.41
     insecto
    -0.41
     Amiens
    -0.41
     hadas
    -0.41
    POSITIVE LOGITS
     roll
    1.34
     rolled
    1.27
     rolling
    1.25
     rolls
    1.25
     Roll
    1.22
    Roll
    1.19
    roll
    1.16
     Rolling
    1.14
     ROLL
    1.13
    Rolling
    1.11
    Activations Density 0.094%

    No Known Activations