© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14943
    Prev
    Next
    INDEX
    Explanations

    phrases related to high speeds or velocity

    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
    2034
    +0.14
    0.4%
    1150
    +0.11
    0.3%
    1819
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1819
    +0.14
    0.05
    1086
    +0.11
    0.03
    1110
    +0.10
    0.02
    Negative Logits
     Nö
    -0.92
     ridu
    -0.91
     allarg
    -0.86
     rispond
    -0.86
     chiaramente
    -0.86
     parteci
    -0.85
     gius
    -0.85
     chied
    -0.84
     préc
    -0.83
     pluri
    -0.83
    POSITIVE LOGITS
     tawny
    0.59
     purée
    0.58
     purplish
    0.56
     greyish
    0.56
     mossy
    0.55
     fringed
    0.54
     grayish
    0.53
     idealized
    0.53
     fuchsia
    0.53
     glabrous
    0.52
    Activations Density 0.141%

    No Known Activations