© 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. 2480
    Prev
    Next
    INDEX
    Explanations

    links to web pages with specific patterns such as numbers and domain names

    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
    1978
    +0.16
    0.5%
    1967
    +0.14
    0.4%
    227
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1527
    +0.16
    0.03
    1471
    +0.14
    0.04
    1343
    +0.13
    0.04
    Negative Logits
     saurait
    -0.85
     prouve
    -0.73
    daß
    -0.69
    Sklici
    -0.68
     pourrais
    -0.65
     dirait
    -0.65
     voudrais
    -0.65
     dépasse
    -0.64
     ferait
    -0.64
     prends
    -0.63
    POSITIVE LOGITS
     ?...
    0.98
     unil
    0.93
     !...
    0.91
     effe
    0.88
     yaa
    0.86
     invari
    0.85
     contex
    0.84
     erad
    0.83
     aton
    0.83
     unden
    0.82
    Activations Density 0.092%

    No Known Activations