© 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. 3518
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and software terms

    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
    1343
    +0.27
    1.1%
    1577
    +0.22
    0.9%
    674
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.27
    0.09
    163
    +0.22
    0.02
    184
    +0.17
    0.01
    Negative Logits
     Pyrene
    -1.15
     Thos
    -1.13
     Middles
    -1.10
     unve
    -1.09
     impra
    -1.09
     Shakspeare
    -1.08
     Glou
    -1.06
     Abbé
    -1.05
     wherea
    -1.04
     ecru
    -1.04
    POSITIVE LOGITS
    XmlEnum
    0.53
    glMatrixMode
    0.48
    SafeAreaView
    0.46
    ipedi
    0.46
     validamos
    0.45
    原始内容存档
    0.45
     parceiros
    0.45
     TEMPLATE
    0.44
    contentLoaded
    0.44
     imparare
    0.43
    Activations Density 1.184%

    No Known Activations