© 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. 3365
    Prev
    Next
    INDEX
    Explanations

    references to videos or visual media elements

    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
    1870
    +0.15
    0.6%
    871
    +0.14
    0.5%
    1464
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1464
    +0.15
    0.05
    871
    +0.14
    0.04
    1133
    +0.12
    0.04
    Negative Logits
    cciale
    -0.65
    Παραπομπές
    -0.54
    AfterEach
    -0.54
    illaume
    -0.52
    ysacchar
    -0.51
    thinkable
    -0.49
     phthalate
    -0.47
    Gambas
    -0.47
     CascadeType
    -0.46
    trà
    -0.45
    POSITIVE LOGITS
     video
    1.27
    video
    1.23
    Video
    1.10
     Video
    1.09
     videos
    1.08
    videos
    0.96
     VIDEO
    0.95
    VIDEO
    0.95
     vidéo
    0.95
     Videos
    0.94
    Activations Density 0.084%

    No Known Activations