© 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. 14574
    Prev
    Next
    INDEX
    Explanations

    words related to technology and global trends

    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
    1810
    +0.10
    0.3%
    900
    +0.08
    0.3%
    1052
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1243
    +0.10
    0.03
    538
    +0.08
    0.03
    286
    +0.08
    0.02
    Negative Logits
    Curs
    -0.49
    <bos>
    -0.47
    Ded
    -0.46
    Aggi
    -0.46
    cuno
    -0.44
    FML
    -0.43
    Eksteraj
    -0.43
     davanti
    -0.43
    ahul
    -0.43
     intégral
    -0.43
    POSITIVE LOGITS
     intersper
    0.88
     levis
    0.79
     pervasive
    0.76
     ftu
    0.74
     rodriguez
    0.72
     hansen
    0.72
     nicolas
    0.71
     herrera
    0.70
     eduardo
    0.69
     posX
    0.68
    Activations Density 0.157%

    No Known Activations