© 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. 14324
    Prev
    Next
    INDEX
    Explanations

    specific terms or phrases related to technical instructions and specifications

    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
    +0.17
    0.5%
    678
    +0.12
    0.4%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.17
    0.04
    1325
    +0.12
    0.03
    468
    +0.10
    0.04
    Negative Logits
    relenting
    -0.63
    mistak
    -0.62
    wavering
    -0.60
     what
    -0.59
    conditionally
    -0.55
    what
    -0.54
    compromising
    -0.54
    What
    -0.52
    ruly
    -0.52
    paralleled
    -0.52
    POSITIVE LOGITS
     fei
    0.96
    Noice
    0.95
     fta
    0.92
     ftu
    0.92
     sappi
    0.89
     fup
    0.87
     fign
    0.87
     fep
    0.87
     Intere
    0.84
     Simult
    0.84
    Activations Density 0.248%

    No Known Activations