© 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. 13726
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming and functions

    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
    453
    +0.16
    0.5%
    1445
    +0.14
    0.4%
    1871
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1871
    +0.16
    0.03
    453
    +0.14
    0.03
    1317
    +0.14
    0.03
    Negative Logits
     Juf
    -1.21
     thut
    -1.14
     fta
    -1.08
     akut
    -1.04
     kompres
    -1.04
     mikrofon
    -1.03
     silikon
    -1.01
     eksklu
    -0.96
     maneu
    -0.96
     gsx
    -0.96
    POSITIVE LOGITS
    <bos>
    1.15
    Pozdrawiam
    0.75
     Roskov
    0.74
    Autoritní
    0.71
    pozdrawiam
    0.71
    Wię
    0.70
    Zgod
    0.68
    ější
    0.68
     spos
    0.67
    Postup
    0.67
    Activations Density 0.064%

    No Known Activations