© 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. 13072
    Prev
    Next
    INDEX
    Explanations

    technical instructions and medical terms related to emergency situations

    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
    468
    +0.13
    0.4%
    1043
    +0.10
    0.3%
    876
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    977
    +0.13
    0.04
    1919
    +0.10
    0.05
    1043
    +0.09
    0.04
    Negative Logits
     дописавши
    -0.69
    <bos>
    -0.60
     poliuret
    -0.54
     gó
    -0.54
     poliester
    -0.54
    Jeografia
    -0.53
    piram
    -0.53
     Paglinawan
    -0.51
     grà
    -0.51
    MarshalTo
    -0.51
    POSITIVE LOGITS
     impra
    1.07
     intersper
    1.05
     overcrow
    1.04
     hairc
    1.04
     outlander
    1.03
     ftre
    1.02
     milf
    1.02
     cushi
    1.01
     pegasus
    1.00
     shenan
    1.00
    Activations Density 0.403%

    No Known Activations