© 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. 14086
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    517
    +0.13
    0.4%
    545
    +0.12
    0.4%
    1896
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.13
    0.04
    545
    +0.12
    0.04
    1557
    +0.12
    0.03
    Negative Logits
    Ehh
    -0.53
    Fuckin
    -0.53
    Lma
    -0.52
     notor
    -0.52
     Ramírez
    -0.51
    Dzi
    -0.49
     dili
    -0.48
     rutin
    -0.48
    jacent
    -0.47
    Uhh
    -0.46
    POSITIVE LOGITS
     vété
    0.81
    ="?
    0.81
     télécharge
    0.76
     identifiant
    0.75
     bénéficiaire
    0.71
     LXXX
    0.71
     pères
    0.69
     XXXVII
    0.69
     chré
    0.67
    ?.
    0.66
    Activations Density 0.139%

    No Known Activations